Daze Lu's repositories
RaspberryPi-yolov5-object-detection
使用树莓派结合yolov5实现目标检测
Chinese_English_Coreference_Resolution
Chinese and english coreference resolution based on SpanBERT and BERT
coding_model_by_hands
手写模型，从零开始
daze_utils
the utils usually used
Experiments
some expriments will be checked
FileBridge
transfer files in different palteforms
human_eval
Run evaluation on LLMs using human-eval benchmark
Language:PythonMIT000
LLaMA-Factory
Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)
Language:PythonApache-2.0000
llama-recipes
Examples and recipes for Llama 2 model
Language:Jupyter NotebookNOASSERTION000
LLMs-FineTuning
The goal to fine tuning llama, mistral, mixtral or other large language models
lm-evaluation-harness
A framework for few-shot evaluation of language models.
Language:PythonMIT000
opencompass
OpenCompass is an LLM evaluation platform, supporting a wide range of models (InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
Language:PythonApache-2.0000